ARTÍCULO
TITULO

RSPCN: Super-Resolution of Digital Elevation Model Based on Recursive Sub-Pixel Convolutional Neural Networks

Ruichen Zhang    
Shaofeng Bian and Houpu Li    

Resumen

The digital elevation model (DEM) is known as one kind of the most significant fundamental geographical data models. The theory, method and application of DEM are hot research issues in geography, especially in geomorphology, hydrology, soil and other related fields. In this paper, we improve the efficient sub-pixel convolutional neural networks (ESPCN) and propose recursive sub-pixel convolutional neural networks (RSPCN) to generate higher-resolution DEMs (HRDEMs) from low-resolution DEMs (LRDEMs). Firstly, the structure of RSPCN is described in detail based on recursion theory. This paper explores the effects of different training datasets, with the self-adaptive learning rate Adam algorithm optimizing the model. Furthermore, the adding-?zero? boundary method is introduced into the RSPCN algorithm as a data preprocessing method, which improves the RSPCN method?s accuracy and convergence. Extensive experiments are conducted to train the method till optimality. Finally, comparisons are made with other traditional interpolation methods, such as bicubic, nearest-neighbor and bilinear methods. The results show that our method has obvious improvements in both accuracy and robustness and further illustrate the feasibility of deep learning methods in the DEM data processing area.

 Artículos similares

       
 
Tienan Li, Xueting Zeng, Cong Chen, Xiangmin Kong, Junlong Zhang, Ying Zhu, Fan Zhang and He Dong    
In this study, an initial water-rights allocation (IWRA) model is proposed for adjusting the traditional initial water-rights empowerment model based on previous water intake permits, with the aim of improving the productivity of water resources under po... ver más
Revista: Water

 
Jiajia Pan and Hung Tao Shen    
A two-dimensional wave model coupled with ice dynamics is developed to evaluate ice effects on shallow water wave propagation on a beach and in a channel. The nonlinear Boussinesq equations with ice effects are derived and solved by the hybrid technique ... ver más
Revista: Water

 
Haoran Liu, Kehui Xu, Bin Li, Ya Han and Guandong Li    
Machine learning classifiers have been rarely used for the identification of seafloor sediment types in the rapidly changing dredge pits for coastal restoration. Our study uses multiple machine learning classifiers to identify the sediment types of the C... ver más
Revista: Water

 
Masoud Jafari Shalamzari, Wanchang Zhang, Atefeh Gholami and Zhijie Zhang    
Site selection for runoff harvesting at large scales is a very complex task. It requires inclusion and spatial analysis of a multitude of accurately measured parameters in a time-efficient manner. Compared with direct measurements of runoff, which is tim... ver más
Revista: Water

 
M.H.J.P. Gunarathna, Kazuhito Sakai, Tamotsu Nakandakari, Kazuro Momii and M.K.N. Kumari    
Poor data availability on soil hydraulic properties in tropical regions hampers many studies, including crop and environmental modeling. The high cost and effort of measurement and the increasing demand for such data have driven researchers to search for... ver más
Revista: Water